Regression Models for Output Prediction of Thermal Dynamics in Buildings

TL;DR

This paper explores the use of nonlinear regression models for predicting thermal dynamics in buildings, showing that considering nonlinear effects improves accuracy and energy efficiency over standard linear models.

Contribution

It introduces analytically derived nonlinear regression models for building thermal dynamics and demonstrates their advantages over standard linear models in prediction accuracy and energy savings.

Findings

Nonlinear regression models improve prediction accuracy.

Considering nonlinear effects reduces power consumption.

Models tested using EnergyPlus simulator.

Abstract

Standard (black-box) regression models may not necessarily suffice for accurate identification and prediction of thermal dynamics in buildings. This is particularly apparent when either the flow rate or the inlet temperature of the thermal medium varies significantly with time. To this end, this paper analytically derives, using physical insight, and investigates linear regression models with nonlinear regressors for system identification and prediction of thermal dynamics in buildings. Comparison is performed with standard linear regression models with respect to both a) identification error, and b) prediction performance within a model-predictive-control implementation for climate control in a residential building. The implementation is performed through the EnergyPlus building simulator and demonstrates that a careful consideration of the nonlinear effects may provide significant benefits with respect to the power consumption.